English
Related papers

Related papers: Towards More Effective and Economic Sparsely-Activ…

200 papers

Mixture-of-Experts (MoE) architectures employ sparse activation to deliver faster training and inference with higher accuracy than dense LLMs. However, in production serving, MoE models require batch inference to optimize hardware…

Machine Learning · Computer Science 2026-02-10 Juntong Wu , Jialiang Cheng , Fuyu Lv , Ou Dan , Li Yuan

Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without…

Sound · Computer Science 2021-05-10 Zhao You , Shulin Feng , Dan Su , Dong Yu

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

Machine Learning · Computer Science 2024-06-06 Amit Dhurandhar , Tejaswini Pedapati , Ronny Luss , Soham Dan , Aurelie Lozano , Payel Das , Georgios Kollias

The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active on a per-example basis, has been proposed in theory as a way of dramatically…

Machine Learning · Computer Science 2017-01-24 Noam Shazeer , Azalia Mirhoseini , Krzysztof Maziarz , Andy Davis , Quoc Le , Geoffrey Hinton , Jeff Dean

Large Language Models (LLMs) have achieved remarkable success with their billion-level parameters, yet they incur high inference overheads. The emergence of activation sparsity in LLMs provides a natural approach to reduce this cost by…

Computation and Language · Computer Science 2024-12-13 Haizhong Zheng , Xiaoyan Bai , Xueshen Liu , Z. Morley Mao , Beidi Chen , Fan Lai , Atul Prakash

Recent large language models (LLMs) have tended to leverage sparsity to reduce computations, employing the sparsely activated mixture-of-experts (MoE) technique. MoE introduces four modules, including token routing, token communication,…

Machine Learning · Computer Science 2025-01-22 Xinglin Pan , Wenxiang Lin , Lin Zhang , Shaohuai Shi , Zhenheng Tang , Rui Wang , Bo Li , Xiaowen Chu

The surgence of Mixture of Experts (MoE) in Large Language Models promises a small price of execution cost for a much larger model parameter count and learning capacity, because only a small fraction of parameters are activated for each…

Sparse Mixture-of-Experts (MoE) models scale capacity by routing each token to a small subset of experts. However, their routers exhibit a fundamental trade-off: strong load balancing can suppress expert specialization, while aggressive…

Machine Learning · Computer Science 2026-05-12 Gleb Molodtsov , Alexander Miasnikov , Aleksandr Beznosikov

In the past year, large (>100B parameter) mixture-of-expert (MoE) models have become increasingly common in the open domain. While their advantages are often framed in terms of efficiency, prior work has also explored functional…

Machine Learning · Computer Science 2025-05-22 Matthew Lyle Olson , Neale Ratzlaff , Musashi Hinck , Man Luo , Sungduk Yu , Chendi Xue , Vasudev Lal

Large language models have transformed many applications but remain expensive to train. Sparse Mixture of Experts (MoE) addresses this through conditional computation, with Expert Parallel (EP) as the standard distributed training method.…

Machine Learning · Computer Science 2026-02-05 Chenwei Cui , Rockwell Jackson , Benjamin Joseph Herrera , Ana María Tárano , Hannah Kerner

The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing. Despite the success, most existing…

Machine Learning · Computer Science 2024-07-26 Hao Zhao , Zihan Qiu , Huijia Wu , Zili Wang , Zhaofeng He , Jie Fu

Mixture-of-Experts (MoE) models have become a key approach for scaling large language models efficiently by activating only a subset of experts during training and inference. Typically, the number of activated experts presents a trade-off:…

Machine Learning · Computer Science 2025-09-04 Yifei He , Yang Liu , Chen Liang , Hany Hassan Awadalla

Artificial neural networks open up unprecedented machine learning capabilities at the cost of ever growing computational requirements. Sparsifying the parameters, often achieved through weight pruning, has been identified as a powerful…

Machine Learning · Computer Science 2024-11-28 Rishav Mukherji , Mark Schöne , Khaleelulla Khan Nazeer , Christian Mayr , Anand Subramoney

Multilingual machine translation has attracted much attention recently due to its support of knowledge transfer among languages and the low cost of training and deployment compared with numerous bilingual models. A known challenge of…

Computation and Language · Computer Science 2022-01-25 Hongyu Gong , Xian Li , Dmitriy Genzel

Scaling the capacity of language models has consistently proven to be a reliable approach for improving performance and unlocking new capabilities. Capacity can be primarily defined by two dimensions: the number of model parameters and the…

Machine Learning · Computer Science 2025-07-04 Samira Abnar , Harshay Shah , Dan Busbridge , Alaaeldin Mohamed Elnouby Ali , Josh Susskind , Vimal Thilak

Large language models (LLMs) have demonstrated proficiency across various natural language processing (NLP) tasks but often require additional training, such as continual pre-training and supervised fine-tuning. However, the costs…

Computation and Language · Computer Science 2024-06-07 Da Ma , Lu Chen , Pengyu Wang , Hongshen Xu , Hanqi Li , Liangtai Sun , Su Zhu , Shuai Fan , Kai Yu

A pivotal advancement in the progress of large language models (LLMs) is the emergence of the Mixture-of-Experts (MoE) LLMs. Compared to traditional LLMs, MoE LLMs can achieve higher performance with fewer parameters, but it is still hard…

Computation and Language · Computer Science 2024-05-31 Xudong Lu , Qi Liu , Yuhui Xu , Aojun Zhou , Siyuan Huang , Bo Zhang , Junchi Yan , Hongsheng Li

Exploiting activation sparsity is a promising approach to significantly accelerating the inference process of large language models (LLMs) without compromising performance. However, activation sparsity is determined by activation functions,…

Machine Learning · Computer Science 2024-06-12 Yixin Song , Haotong Xie , Zhengyan Zhang , Bo Wen , Li Ma , Zeyu Mi , Haibo Chen

Mixture-of-Experts (MoE) represents an ensemble methodology that amalgamates predictions from several specialized sub-models (referred to as experts). This fusion is accomplished through a router mechanism, dynamically assigning weights to…

Machine Learning · Computer Science 2024-03-27 Jinze Zhao , Peihao Wang , Zhangyang Wang

We introduce, Q-Sparse, a simple yet effective approach to training sparsely-activated large language models (LLMs). Q-Sparse enables full sparsity of activations in LLMs which can bring significant efficiency gains in inference. This is…

Computation and Language · Computer Science 2024-07-25 Hongyu Wang , Shuming Ma , Ruiping Wang , Furu Wei